222 Open source projects that are alternatives of or similar to D-TDNN

DropClass and DropAdapt - repository for the paper accepted to Speaker Odyssey 2020

Pytorch implementation of Generalized End-to-End Loss for speaker verification

Trained speaker embedding deep learning models and evaluation pipelines in pytorch and tesorflow for speaker recognition.

neural network based speaker embedder

Official open source implementation of the paper "Overlap-aware low-latency online speaker diarization based on end-to-end local segmentation"

Scripts for LIUM SpkDiarization tools

A program for automatic speaker identification using deep learning techniques.

Code for our ACML and INTERSPEECH papers: "Speaker Diarization as a Fully Online Bandit Learning Problem in MiniVox".

This repo contains my attempt to create a Speaker Recognition and Verification system using SideKit-1.3.1

Bob is a free signal-processing and machine learning toolbox originally developed by the Biometrics group at Idiap Research Institute, in Switzerland. - Mirrored from https://gitlab.idiap.ch/bob/bob

Develop speaker recognition model based on i-vector using TIMIT database

UniSpeech - Large Scale Self-Supervised Learning for Speech

Share some recent speaker recognition papers and their implementations.

Kaldi based speaker verification

Keras Implementation of Deepmind's WaveNet for Supervised Learning Tasks

DELTA is a deep learning based natural language and speech processing platform.

Pytorch implementation of Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs (Interspeech, 2020)

🔭 Speaker diarization via transfer learning

kaldi-asr/kaldi is the official location of the Kaldi project.

A Deep Graph Neural Network Architecture for Modelling Spatio-temporal Dynamics in rs-fMRI Data

Unofficial Implementation of Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration

Collection of auditory models.

Continuous Augmented Positional Embeddings (CAPE) implementation for PyTorch

CVC: Contrastive Learning for Non-parallel Voice Conversion (INTERSPEECH 2021, in PyTorch)

Official implementation of Meta-StyleSpeech and StyleSpeech

ICASSP 2019 official Latex template

This application is developed to help speechless people interact with others with ease. It detects voice and converts the input speech into a sign language based video.

Docker image and scripts for training finetuned or completely personal Kaldi speech models. Particularly for use with kaldi-active-grammar.

📈 Ventib records your voice, transcribes it in realtime, and performs speech pattern analysis to give you objective statistics about how you speak.

AdaSpeech: Adaptive Text to Speech for Custom Voice

The official repo of "Multi-channel Narrow-band Deep Speech Separation with Full-band Permutation Invariant Training", "Multichannel Speech Separation with Narrow-band Conformer" and "NBC2: Multichannel Speech Separation with Revised Narrow-band Conformer".

It is a complete project of voiceprint recognition or speaker recognition.

a deep accent recognition network

MobileNet trained with VoxCeleb dataset and used for voice verification

PyTorch reimplementation of per-channel energy normalization for audio.

A list of publically available audio data that anyone can download for ASR or other speech activities

https://dodiku.github.io/audio_noise_clustering/results/ ==> An experiment with a variety of clustering (and clustering-like) techniques to reduce noise on an audio speech recording.

Сценарии для системы домашней автоматизации Majordomo

Pitch shifter using WSOLA and resampling implemented by Python3

A live speech recognition using Facebooks wav2vec 2.0 model.

Convert text to speech using Google Translate API

target speaker extraction and verification for multi-talker speech

Mobile application for exploring fitness data using both speech and touch interaction.

alternative form of inputs for in-VR interaction with the content of a scene

Speech-to-text and keyboard input captions for OBS.

Voice control for your websites and applications

Source code of the model used in Tensorflow Speech Recognition Challenge (https://www.kaggle.com/c/tensorflow-speech-recognition-challenge). The solution ranked in top 5% in private leaderboard.

TFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesis

An end-to-end system that performs temporal recognition of gesture sequences using speech and skeletal input. The model combines three networks with a CTC output layer that recognises gestures from continuous stream.

Text-to-Speech Toolkit of the Speech and Language Technologies Group at the University of Stuttgart. Objectives of the development are simplicity, modularity, controllability and multilinguality.

Meta-embeddings are a probabilistic generalization of embeddings in machine learning.

A proof-of-concept app using KeenASR SDK on Android. WE ARE HIRING: https://keenresearch.com/careers.html

💬 A speech bubble dialog component for React Native.

A data annotation pipeline to generate high-quality, large-scale speech datasets with machine pre-labeling and fully manual auditing.

A list of publicly available room impulse response datasets and scripts to download them.

Official implementation of VQMIVC: One-shot (any-to-any) Voice Conversion @ Interspeech 2021 + Online playing demo!

Source code (train/test) accompanying the paper entitled "Veritatem Dies Aperit - Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach" in CVPR 2019 (https://arxiv.org/abs/1903.10764).

🎙️ Handsfree Audio Development Interface

speaker diarization system using an LSTM

2019 Clova AI Hackathon : Speech - Rank 12 / Team Kai.Lib